Comparison of multivariate normalization techniques as applied to electronic nose based pattern classification for black tea

An appropriate normalization technique selection is one of the key issues for increasing the accuracy of correct classification for pattern recognition in an electronic nose system. This paper presents a comparative study of different normalization techniques for enhancing pattern classification of black tea using electronic nose. For this study black tea samples were collected from different tea gardens in India. At first principal component analysis (PCA) was used to investigate presence of clusters in the sensors responses in multidimensional space. Then different normalization techniques were used on the black tea data. Finally classification performances were done using BP-MLP. BP-MLP algorithm for black tea classifications using normalized data marginally enhances the pattern recognition accuracy of electronic nose system.